Carding 4 Carders
Professional
- Messages
- 2,724
- Reaction score
- 1,588
- Points
- 113
BTSbot finds and classifies supernovae on its own.
A new artificial intelligence tool called BTSbot completely eliminates human involvement in the search and detection of supernovae. A machine learning algorithm called the Bright Transient Survey Bot (BTSbot) detected, identified and classified its first supernova without human intervention, according to the University of Northwestern. The newly discovered supernova candidate was named SN2023tyk.
This fully automated process was developed by an international team of researchers led by Northwestern University. The program's algorithm was trained on the basis of more than 1.4 million historical images from 16,000 astronomical sources. "For the first time, a series of robots and AI algorithms observed, then identified, and finally confirmed the supernova detection," said Adam Miller of Northwestern University, who led the project.
Miller added that such a discovery will allow robots to identify specific subtypes of stellar explosions and is "an important step forward." "Ultimately, excluding a person from the process gives more time to analyze observations and develop new hypotheses," he stressed.
Supernovae are stars that reach the end of their life cycle and explode, dramatically increasing their brightness. So far, the process of detecting and analyzing these stellar explosions has only been partially automated. Northwestern University estimates that over the past six years, people have spent approximately 2,200 hours visually checking and classifying supernova candidates.
The new tool will allow researchers to devote more time to other tasks, speeding up the pace of discoveries. Nabeel Rehemtulla, who co-led the development with Miller, said: "We have achieved the world's first fully automatic supernova detection, identification and classification."
A new artificial intelligence tool called BTSbot completely eliminates human involvement in the search and detection of supernovae. A machine learning algorithm called the Bright Transient Survey Bot (BTSbot) detected, identified and classified its first supernova without human intervention, according to the University of Northwestern. The newly discovered supernova candidate was named SN2023tyk.
This fully automated process was developed by an international team of researchers led by Northwestern University. The program's algorithm was trained on the basis of more than 1.4 million historical images from 16,000 astronomical sources. "For the first time, a series of robots and AI algorithms observed, then identified, and finally confirmed the supernova detection," said Adam Miller of Northwestern University, who led the project.
Miller added that such a discovery will allow robots to identify specific subtypes of stellar explosions and is "an important step forward." "Ultimately, excluding a person from the process gives more time to analyze observations and develop new hypotheses," he stressed.
Supernovae are stars that reach the end of their life cycle and explode, dramatically increasing their brightness. So far, the process of detecting and analyzing these stellar explosions has only been partially automated. Northwestern University estimates that over the past six years, people have spent approximately 2,200 hours visually checking and classifying supernova candidates.
The new tool will allow researchers to devote more time to other tasks, speeding up the pace of discoveries. Nabeel Rehemtulla, who co-led the development with Miller, said: "We have achieved the world's first fully automatic supernova detection, identification and classification."
